POP-3D introduces a zero-shot open-vocabulary 3D occupancy prediction model leveraging multimodal self-supervised learning, achieving 78% mIoU on nuScenes without manual annotations.

Antonin Vobecky, Oriane Siméoni, David Hurych et al.

SceneVerse constructs a million-scale 3D scene-language dataset and introduces GPS, a contrastive pre-training framework, achieving SOTA in grounded scene understanding.

Baoxiong Jia, Yixin Chen, Huangyue Yu et al.

Proposes fine-tuning spatial modules with high-quality images, enabling high-quality video diffusion training using only low-quality videos and synthetic images.

Haoxin Chen, Yong Zhang, Xiaodong Cun et al.

Introduces multi-track timeline control for text-driven 3D human motion, using a test-time denoising method with pre-trained diffusion models, achieving fine-grained multi-action synthesis.

Mathis Petrovich, Or Litany, Umar Iqbal et al.

TACO constructs a large-scale bimanual tool-action-object dataset supporting generalization tasks with 2.5K sequences and 5.2M frames.

Yun Liu, Haolin Yang, Xu Si et al.

This study uncovers systematic visual shortcomings in multimodal large models, proposing feature fusion strategies to improve visual grounding, validated on the MMVP benchmark.

Shengbang Tong, Zhuang Liu, Yuexiang Zhai et al.

CTNeRF integrates cross-time Transformer and time-frequency feature fusion, significantly improving novel view synthesis from monocular videos of dynamic scenes.

Xingyu Miao, Yang Bai, Haoran Duan et al.

Using Marabou to verify robustness of Airbus runway object classifier; noise sensitivity exceeds brightness and contrast.

Yizhak Elboher, Raya Elsaleh, Omri Isac et al.

GUESS leverages multi-scale skeleton abstraction and cascaded latent diffusion for text-driven human motion synthesis.

Xuehao Gao, Yang Yang, Zhenyu Xie et al.

VideoStudio combines LLM and diffusion models to generate multi-scene videos with content consistency, outperforming SOTA with detailed script and reference image guidance.

Fuchen Long, Zhaofan Qiu, Ting Yao et al.

LLoVi combines short-term visual captions with large models for long video QA, achieving 50.3% accuracy.

Ce Zhang, Taixi Lu, Md Mohaiminul Islam et al.

Segment3D leverages SAM-generated pseudo labels and a two-stage training scheme to achieve high-quality, label-free 3D scene segmentation, outperforming supervised baselines.

Rui Huang, Songyou Peng, Ayca Takmaz et al.

Q-Align trains LMMs with discrete text levels, achieving SOTA in image/video quality assessment.

Haoning Wu, Zicheng Zhang, Weixia Zhang et al.

DL3DV-10K is a large-scale real-world scene dataset with 65 POI categories, 5120万 frames, supporting advanced 3D vision tasks.

Lu Ling, Yichen Sheng, Zhi Tu et al.

VIEScore leverages large multimodal language models for explainable evaluation of conditional image synthesis, achieving a correlation of 0.4 with human judgments.

Max Ku, Dongfu Jiang, Cong Wei et al.

InternVL scales a 6B vision transformer with an 8B multilingual layer, achieving SOTA on 32 visual-linguistic benchmarks.

Zhe Chen, Jiannan Wu, Wenhai Wang et al.

DriveLM integrates graph-structured visual QA with pre-trained VLMs for end-to-end autonomous driving, achieving superior zero-shot generalization on nuScenes and CARLA.

Chonghao Sima, Katrin Renz, Kashyap Chitta et al.

VideoPoet uses a decoder-only Transformer for zero-shot video generation, producing high-quality motions.

Dan Kondratyuk, Lijun Yu, Xiuye Gu et al.

A GPT-4-based multimodal agent achieves 84.4% success on 50 diverse smartphone tasks, operating without backend access.

Chi Zhang, Zhao Yang, Jiaxuan Liu et al.

Align Your Gaussians (AYG) combines dynamic 3D Gaussian splatting with deformation fields and multi-modal diffusion feedback to achieve state-of-the-art text-to-4D scene synthesis, outperforming prior methods.

Huan Ling, Seung Wook Kim, Antonio Torralba et al.